# Web Pentesting (black-box) leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/external-web-pentest-blackbox

OpenAI Web Pentesting, black-box score. Every model the catalog carries a published Web Pentesting (black-box) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Vulnerability recall (Web Blackbox score) |
| Tasks | Black-box web application penetration tests |
| Difficulty | Web vulnerability discovery |
| Published by | [GPT-6 Cyber: Advancing the frontier of aligned cybersecurity agents](https://openai.com/index/introducing-gpt-6-cyber/) |

OpenAI's offensive web penetration-testing evaluation: the model probes web applications without access to their source code and is scored on the share of planted vulnerabilities it finds.

## Web Pentesting (black-box) ranking

2 models with a published Web Pentesting (black-box) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Vulnerability recall (Web Blackbox score) | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Cyber](https://modelscale.dev/models/gpt-6-cyber) | OpenAI | 40.3 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 32.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
